skip to main content
10.1145/2343483.2343488acmconferencesArticle/Chapter ViewAbstractPublication PagessiggraphConference Proceedingsconference-collections
research-article

Virtual texturing in software and hardware

Published:05 August 2012Publication History

ABSTRACT

This course introduces partially resident textures (PRTs), a new GPU feature for virtual texturing, and contrasts them with software-based methods of virtual texturing. PRTs are available in the Southern Islands (Radeon HD 7xxx) family of graphics processors.

The basic idea of virtual texturing is simple: instead of maintaining a separate texture for each object rendered on the screen, all textures are stored in a "virtual texture". The size of the virtual texture is on the order of billions of texels, and each object is assigned unique virtual-texture coordinates from the virtual texture. When used in a shader, the virtual-texture coordinates are translated into physical-texture coordinates, which are used to access the physical texture that contains the working set of all required tiles.

Existing approaches implement the entire virtual texturing algorithm in software. The software is required to update the page table (another texture used for translating virtual texture coordinates to physical ones), perform address translation, and deal with hardware differences when it comes to supported texture types, formats, and filtering modes. The first part of the course outlines this process and discusses difficulties encountered when this technology is deployed in RAGE. PRTs eliminate the need for maintaining the page table and address translation and provide support for all texture types, formats, and filtering modes. The second part of the course describes the hardware architecture as it relates to PRTs. The third part of the course introduce the new AMD sparse-texture OpenGL extension that exposes PRTs to software applications. The course includes several PRT use cases, a technical demo, and a summary of the strengths and weaknesses of PRT technology.

Skip Supplemental Material Section

Supplemental Material

crs110_1_12.mp4

mp4

5.6 MB

crs110_2_12.mp4

mp4

12.7 MB

crs110_3_12.mp4

mp4

12.2 MB

Recommendations

Comments

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Sign in
  • Published in

    cover image ACM Conferences
    SIGGRAPH '12: ACM SIGGRAPH 2012 Courses
    August 2012
    1998 pages
    ISBN:9781450316781
    DOI:10.1145/2343483

    Copyright © 2012 ACM

    Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    • Published: 5 August 2012

    Permissions

    Request permissions about this article.

    Request Permissions

    Check for updates

    Qualifiers

    • research-article

    Acceptance Rates

    Overall Acceptance Rate1,822of8,601submissions,21%

    Upcoming Conference

    SIGGRAPH '24

PDF Format

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader